{"id":"https://openalex.org/W4417073180","doi":"https://doi.org/10.1145/3743093.3770950","title":"Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning","display_name":"Q-Adapter: Visual Query Adapter for Extracting Textually-related Features in Video Captioning","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W4417073180","doi":"https://doi.org/10.1145/3743093.3770950"},"language":"en","primary_location":{"id":"doi:10.1145/3743093.3770950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2510.10022","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110361511","display_name":"J. R. Chen","orcid":"https://orcid.org/0009-0001-3649-8651"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junan Chen","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0009-0001-3649-8651","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101718798","display_name":"Trung Th\u00e0nh Nguy\u1ec5n","orcid":"https://orcid.org/0000-0001-8976-2922"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Trung Thanh Nguyen","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8976-2922","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047823141","display_name":"Takahiro Komamizu","orcid":"https://orcid.org/0000-0002-3041-4330"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Komamizu","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3041-4330","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034941095","display_name":"Ichiro Ide","orcid":"https://orcid.org/0000-0003-3942-9296"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ichiro Ide","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3942-9296","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9927999973297119,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.000699999975040555,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.9462000131607056},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5968000292778015},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.5648999810218811},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.48559999465942383},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4180999994277954},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3862000107765198},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3400000035762787}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.9462000131607056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8802000284194946},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5968000292778015},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.5648999810218811},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48559999465942383},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4180999994277954},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3231000006198883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3222000002861023},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31380000710487366},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C2775941552","wikidata":"https://www.wikidata.org/wiki/Q25212305","display_name":"Isolation (microbiology)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.2809000015258789},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2750999927520752},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27410000562667847},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.26919999718666077},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2653000056743622}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3743093.3770950","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3743093.3770950","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2510.10022","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10022","pdf_url":"https://arxiv.org/pdf/2510.10022","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.10022","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.10022","pdf_url":"https://arxiv.org/pdf/2510.10022","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1573040851","https://openalex.org/W1927052826","https://openalex.org/W1956340063","https://openalex.org/W2078238240","https://openalex.org/W2110933980","https://openalex.org/W2425121537","https://openalex.org/W3035392611","https://openalex.org/W3092714372","https://openalex.org/W3095319910","https://openalex.org/W3138516171","https://openalex.org/W3205021045","https://openalex.org/W3217340782","https://openalex.org/W4206178588","https://openalex.org/W4285606530","https://openalex.org/W4312463400","https://openalex.org/W4312884055","https://openalex.org/W4386066385","https://openalex.org/W4390871765","https://openalex.org/W4402702928","https://openalex.org/W4402702962","https://openalex.org/W4402754238","https://openalex.org/W4404781913","https://openalex.org/W4413146904"],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advances":[1],"in":[2,69,217],"video":[3,106,140],"captioning":[4,107,141],"are":[5],"driven":[6],"by":[7,17,100],"large-scale":[8],"pretrained":[9],"models,":[10],"which":[11],"follow":[12],"the":[13,21,37,54,81,105,152,156,176,185,190,212],"standard":[14],"\u201cpre-training":[15],"followed":[16],"fine-tuning\u201d":[18],"paradigm,":[19],"where":[20,146],"full":[22,177],"model":[23,38],"is":[24],"fine-tuned":[25],"for":[26,104,206,227],"downstream":[27],"tasks.":[28],"Although":[29],"effective,":[30],"this":[31,85],"approach":[32,45,158,179],"becomes":[33],"computationally":[34],"prohibitive":[35],"as":[36],"size":[39],"increases.":[40],"The":[41],"Parameter-Efficient":[42],"Fine-Tuning":[43],"(PEFT)":[44],"offers":[46],"a":[47,91,115],"promising":[48],"alternative,":[49],"but":[50],"primarily":[51],"focuses":[52],"on":[53,130,137,198],"language":[55],"components":[56],"of":[57,76,124,184,192,215],"Multimodal":[58],"Large":[59],"Language":[60],"Models":[61],"(MLLMs).":[62],"Despite":[63],"recent":[64],"progress,":[65],"PEFT":[66,157],"remains":[67],"underexplored":[68],"multimodal":[70],"tasks":[71],"and":[72,114,144,163,195,221],"lacks":[73],"sufficient":[74],"understanding":[75],"visual":[77,93],"information":[78],"during":[79],"fine-tuning":[80,103,178,199],"model.":[82],"To":[83],"bridge":[84],"gap,":[86],"we":[87],"propose":[88],"Query-Adapter":[89],"(Q-Adapter),":[90],"lightweight":[92],"adapter":[94],"module":[95],"designed":[96],"to":[97,172],"enhance":[98],"MLLMs":[99],"enabling":[101,121],"efficient":[102],"task.":[108],"Q-Adapter":[109,136,166,216],"introduces":[110],"learnable":[111],"query":[112],"tokens":[113],"gating":[116],"layer":[117],"into":[118,203],"Vision":[119],"Encoder,":[120],"effective":[122],"extraction":[123],"sparse,":[125],"caption-relevant":[126],"features":[127],"without":[128],"relying":[129],"external":[131],"textual":[132],"supervision.":[133],"We":[134,187],"evaluate":[135],"two":[138],"well-known":[139],"datasets,":[142],"MSR-VTT":[143],"MSVD,":[145],"it":[147],"achieves":[148,168],"state-of-the-art":[149],"performance":[150,170],"among":[151],"methods":[153,173],"that":[154,174],"take":[155,175],"across":[159],"BLEU@4,":[160],"METEOR,":[161],"ROUGE-L,":[162],"CIDEr":[164],"metrics.":[165],"also":[167],"competitive":[169],"compared":[171],"while":[180],"requiring":[181],"only":[182],"1.4%":[183],"parameters.":[186],"further":[188],"analyze":[189],"impact":[191],"key":[193],"hyperparameters":[194],"design":[196],"choices":[197],"effectiveness,":[200],"providing":[201],"insights":[202],"optimization":[204],"strategies":[205],"adapter-based":[207],"learning.":[208],"These":[209],"results":[210],"highlight":[211],"strong":[213],"potential":[214],"balancing":[218],"caption":[219],"quality":[220],"parameter":[222],"efficiency,":[223],"demonstrating":[224],"its":[225],"scalability":[226],"video\u2013language":[228],"modeling.":[229]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-15T00:00:00"}